• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2011년도 춘계학술발표대회
• /
• pp.378-381
• /
• 2011

These days rapid improvement in Mobile phones and their multimedia limits made them powerful enough to manage complicated tasks. Image processing related support for mobile devices is extremely comprehensive in wireless telemedicine. A basic challenge is how to get best quality of image with the limited screen size and resources of mobile phones. This paper deals with image processing features (capturing rendering and zooming in and out) of Mobile Media API and Advanced Multimedia Supplements (MMAPI and AMS) developed for Mobile Java Platform and customized algorithm is designed to keep all image task cost efficient by using minimum device resources and memory. This scenario is driven by the need for evaluation of a distant patient that cannot be moved to the expert.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 춘계학술발표대회
• /
• pp.479-481
• /
• 2023

Generative Adversarial Networks (GANs) have facilitated substantial improvement in single-image super-resolution (SR) by enabling the generation of photo-realistic images. However, the high memory requirements of GAN-based SRs (mainly generators) lead to reduced performance and increased energy consumption, making it difficult to implement them onto resource-constricted devices. In this study, we propose an efficient and compressed architecture for the SR-GAN (generator) model using the model compression technique Knowledge Distillation. Our approach involves the transmission of knowledge from a heavy network to a lightweight one, which reduces the storage requirement of the model by 58% with also an increase in their performance. Experimental results on various benchmarks indicate that our proposed compressed model enhances performance with an increase in PSNR, SSIM, and image quality respectively for x4 super-resolution tasks.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 추계학술발표대회
• /
• pp.605-607
• /
• 2023

Recent research has highlighted the effectiveness of Deep Learning (DL) techniques in automating the detection of lung sound anomalies. However, the available lung sound datasets often suffer from limitations in both size and balance, prompting DL methods to employ data preprocessing such as augmentation and transfer learning techniques. These strategies, while valuable, contribute to the increased complexity of DL models and necessitate substantial training memory. In this study, we proposed a streamlined and lightweight DL method but effectively detects lung sound anomalies from small and imbalanced dataset. The utilization of 1D dilated convolutional neural networks enhances sensitivity to lung sound anomalies by efficiently capturing deep temporal features and small variations. We conducted a comprehensive evaluation of the ICBHI dataset and achieved a notable improvement over state-of-the-art results, increasing the average score of sensitivity and specificity metrics by 2.7%.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 추계학술발표대회
• /
• pp.1016-1017
• /
• 2023

이 연구는 ADHD 환자를 대상으로 디지털 치료 게임을 개발하였으며, 환자의 주의력과 기억력을 향상시키도록 구성되었다. 게임은 눈 움직임과 ADHD 의 연관성을 고려하여 아이트래킹 기술을 활용하여 개발되었다. 이를 통해 ADHD 환자를 위한 맞춤형 디지털 치료 게임의 중요성을 강조한다.

• International Journal of Advanced Culture Technology
• /
• 제12권3호
• /
• pp.466-470
• /
• 2024

This study proposes a deep learning-based LSTM model to predict the state of charge (SOC) of lithium-ion batteries. The model was trained using data collected under various temperature and load conditions, including measurement data from the CS2 lithium-ion battery provided by the University of Maryland College of Engineering. The LSTM model effectively models temporal patterns in the data by learning long-term dependencies. Performance evaluation by epoch showed that the predicted SOC improved from 14.8400 at epoch 10 to 12.4968 at epoch 60, approaching the actual SOC value of 13.5441. The mean absolute error (MAE) and root mean squared error (RMSE) also decreased from 0.9185 and 1.3009 at epoch 10 to 0.2333 and 0.5682 at epoch 60, respectively, indicating continuous improvement in predictive performance. This study demonstrates the validity of the LSTM model for predicting the SOC of lithium-ion batteries and its potential to enhance battery management systems.

• 한국실내디자인학회논문집
• /
• 제24권1호
• /
• pp.43-53
• /
• 2015

As part of alternative of elderly problems in the future super-aging society, this study aims to extract an improvement plan of interior environment design of Seoul-type day care centers to expand in future by observing day care centers as medical and healing environments, from the perspective of user experience. For this study, after selecting major activity areas of representative cases of Seoul-type day care centers, user behaviors in the space were observed and 4 seniors of baby-boom generation who are potential uses were chosen as personas by reflecting characteristics of healthy elderly, physical aging, mental aging and infirm elderly, from the perspective of user experience. Based on previous studies on healing environments, these characteristics and demands of personas were classified into environmental aspects, physical aspects and mental aspects to extract an improvement plan. The study results are as follows. First, interior environment design reflecting persona characteristics helps the elderly adapt to the environment and provides a comfortable environment like home for stability, treatment and recovery of memory. Second, interior environment design reflecting persona characteristics helps psychological healing through light entering the large windows and natural environment elements. Third, for interior environment design reflecting persona characteristics, finish materials with bright and soft colors should be used to change the images of facilities positively. Fourth, spatial composition should be remedied through division of space and built-in furniture depending on the needs of users for loitering of extra time and programs.

• 대한간호학회지
• /
• 제47권1호
• /
• pp.1-13
• /
• 2017

Purpose: The purpose of this study was to examine the effects of a cognitive training program on neurocognitive task performance and activities of daily living (ADL) in patients who had a stroke. Methods: The research design for this study was a nonequivalent control group non-synchronized design. Patients were assigned to the experimental (n=21) or control group (n=21). The experimental group received a 4-week cognitive training program and usual care (i.e., rehabilitation service), while the control was received usual care only. Cognitive function was measured with a standardized neurocognitive test battery and ADL was assessed at baseline and one and two months after completion of the intervention. Repeated measures ANOVA was used to determine changes in cognitive function and ADL over 2 months. Results: The interaction of group and time was significant indicating that the experimental group showed improvement in attention, visuospatial function, verbal memory, and executive function compared to the control group which had a sustained or gradual decrease in test performance. A significant group by time interaction in instrumental ADL was also found between the experimental group with gradual improvement and the control group showing no noticeable change. Conclusion: Findings show that the cognitive training program developed in this study is beneficial in restoring cognitive function and improving ADL in patients following a stroke. Further study is needed to investigate the long-term relationship between cognitive training participation and cognitive improvement and effective functioning in daily living.

• 동의신경정신과학회지
• /
• 제9궈1호
• /
• pp.25-43
• /
• 1998

45 Dementia of Alzheimer type patients who were treated by the KOMC NP from Jan. 1996 to July. 1997 were recruited for this study in order to prove the effects of the oriental medical treatment on Dementia of Alzheimer type. Patients were strictly classified into Sasang constitutions, and then were given herbal and acupunctural treatment for various length of time. The efficiency of the treatment was assessed by criteria for memory, orientation, registration, attention and calculation, language. The following results were obtained. 1. Out of 45 cases, 14 improved to almost normal state, 13 improved a little, 16 had no change, and 2 became worse. On the whole, 60% of the patients showed improvement. 2. Out of 31 female patients, 17 patients improved, thus the rate of improvement was at 55%. Out of 14 male patients, 10 patients improved, thus the rate of improvement was at 71%. 3. The analysis of the patients constitution resulted in two Soyang-constitution, 23 Soum and 20 Taeum, Soum, Teaum responded to the treatment to an approximately equal extent. 4. Of the demendia patients involved in the study, 9 cases were mild, 14 moderate, and 22 severe, 9 mild cases, 12 moderate cases and 6 severe cases showed meaningful response to the treatment.

• 대한지역사회작업치료학회지
• /
• 제4권2호
• /
• pp.75-83
• /
• 2014

목적 : 본 연구는 강원도 태백지역에 거주하는 초기치매환자를 대상으로 실시한 방문 인지 작업치료 프로그램의 효과를 알아보고자 하였다. 연구방법 : 초기치매환자 30명을 대상으로 작업치료학과 학생 30명과 자원봉사자들이 주 1회 총 8회기의 가정방문 인지작업치료 중재를 실시하였다. 프로그램 전후의 대상자들의 인기기능의 변화를 알아보기 위해 MMSE-K를 사용하여 측정하였다. 또한 가정방문 인지작업치료에 대한 초기치매 환자들의 인식과 만족도를 확인하였다. 결과 : 초기 치매환자에게 가정방문 인지작업치료 적용한 결과 전반적인 인지기능의 향상이 나타났으며 특히 지남력, 기억회상, 주의집중력, 언어력의 경우 통계학적으로 유의한 향상이 나타났다. 결론 : 인지기능의 향상과 일상생활능력의 향상을 위한 가정방문 작업치료 프로그램이 치매환자의 중재에 있어 유용하게 적용될 것으로 사료되며 향후 가정방문 작업치료 서비스 도입을 위한 다양한 가정방문 작업치료 중재 프로그램 개발이 필요하다.

• 한국정보처리학회논문지
• /
• 제2권4호
• /
• pp.592-602
• /
• 1995

자동 배선 시스템의 배선영역 모델링 방법은 논-그리드(non-grid)와 그리드 방식 을 사용하고 있다. 본 논문에서는 라우팅 속도를 개선하기 위해 논-그리드와 그리드 방식을 혼합하여 자동 배선 시스템을 개발 하였다. 그리드방식은 PCB상에 전기적, 물 리적 요소들이 적다 할지라도 보드와 그리드의 크기에 제약을 받기 때문에 메모리가 많아지게 되어 자동 배선 속도를 감소시키는 단점을 가지고 있고, 논-그리드 방식은 shape-based 방식의 영역 처리방식을 사용하므로 메모리를 상당히 적게 소요된다. 그러므로 본 논문에서는 논-그리드 방식과 그리드 방식을 적용하여 초기 배선시에는 전자를 적용해 속도를 개선시켰고, 초기 배선시 연결되지 않은 배선은 후자를 적용해 서 완전한 배선이 이루어 질 수 있도록 하였다. 따라서, 본 시스템을 이와 같은 방식 을 이용하여 IBM 486DX2-66 컴퓨터의 Windows NT 환경하에서 Borland C＋＋로 개발하 였다.